© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41776
    Prev
    Next
    INDEX
    Explanations

    HTML/JS panel components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⮜
    -2.28
    灃
    -2.14
     was
    -2.06
    zelfde
    -2.05
    暻
    -1.92
     použití
    -1.92
    🧌
    -1.92
    쫀
    -1.88
     legitimately
    -1.87
    ecta
    -1.84
    POSITIVE LOGITS
    With
    2.80
    This
    2.75
    What
    2.70
    If
    2.64
    It
    2.63
    These
    2.55
    They
    2.55
    There
    2.53
    By
    2.47
    Since
    2.42
    Activations Density 0.003%

    No Known Activations